© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43556
    Prev
    Next
    INDEX
    Explanations

    whole thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verhind
    0.21
    uerung
    0.20
     additional
    0.20
     eradicated
    0.19
    主持人
    0.19
    れています
    0.18
     hindering
    0.18
    甪
    0.18
    additional
    0.18
     Ն
    0.17
    POSITIVE LOGITS
     ఒకటి
    0.22
    фри
    0.21
     пишет
    0.20
    ickou
    0.20
     conventionally
    0.20
    icollis
    0.19
     fréquente
    0.19
     كلهم
    0.19
    지와
    0.19
    সিক
    0.19
    Activations Density 0.010%

    No Known Activations